Processing system and method for rare-disease medical data
The distributed computing system addresses data scarcity and confidentiality issues in rare-disease analysis by integrating federated learning and particle swarm optimization, ensuring privacy and improving training efficiency and accuracy.
US20260141138A1Pending Publication Date: 2026-05-21PEKING UNION MEDICAL COLLEGE HOSPITAL +1
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- US · United States
- Patent Type
- Applications(United States)
- Current Assignee / Owner
- PEKING UNION MEDICAL COLLEGE HOSPITAL
- Filing Date
- 2025-11-19
- Publication Date
- 2026-05-21
AI Technical Summary
Technical Problem
Medical institutions face challenges in analyzing rare-disease data due to data scarcity and confidentiality, leading to increased training difficulty and hardware resource demands.
Method used
A distributed computing system utilizing a federated learning model training mechanism and particle swarm optimization algorithm to integrate model training with disease diagnosis, ensuring data privacy and reducing training difficulty while enhancing efficiency and accuracy.
Benefits of technology
The system improves the execution efficiency of distributed computing tasks, reduces data transmission load, and enhances recognition accuracy by avoiding local optima through iterative updates and end-to-end encryption.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure US20260141138A1-D00000_ABST
Abstract
A processing system and method for rare-disease medical data are provided, where a server, based on a medical data analysis request initiated by a target client, generates global model parameters and an initial analysis model, and sends the global model parameters and the initial analysis model to a plurality of clients; each client trains the initial analysis model based on client-side medical data of the client, and sends local model parameters and loss function values of the local analysis model to the server; the server inputs a plurality of the local model parameters and the loss function values received in a current round into a particle swarm optimization model, so as to obtain optimized model parameters output by the particle swarm optimization model; the server determines whether the optimized model parameters meet a preset condition, wherein if no, the optimized model parameters are sent to each client.
Need to check novelty before this filing date? Find Prior Art